Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add hamzaPixl/pixl-ai --skill task-persistgit clone --depth 1 https://github.com/hamzaPixl/pixl-aiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hamzapixl/pixl-ai/task-persist)<a href="https://agentmods.dev/skills/hamzapixl/pixl-ai/task-persist"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/task-persist/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hamzapixl/pixl-ai/task-persist"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/task-persist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00032 | $0.00667 |
| Opus 5.5 | $0.00013 | $0.00267 |
| Sonnet 5.5 | $0.00006 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
task-persist scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
This skill persists task state to .context/task-state.json so work can resume across sessions.
Step 1: Determine Mode
If argument is save (or no tasks exist in TaskList):
→ Go to Step 2 (Save)
If argument is load (or .context/task-state.json exists):
→ Go to Step 3 (Load)
Step 2: Save Task State
- Call
TaskListto get all current tasks - For each task, call
TaskGetto get full details - Write the complete task state to
.context/task-state.json:
{
"savedAt": "ISO timestamp",
"sessionId": "auto-generated",
"tasks": [
{
"id": "original-id",
"subject": "...",
"description": "...",
"status": "pending|in_progress|completed",
"blockedBy": ["id1", "id2"],
"blocks": ["id3"]
}
]
}
- Validate dependency graph before saving:
python3 -c " import json, sys try: from pixl.utils.task_graph import validate_task_graph tasks = json.load(open('.context/task-state.json'))['tasks'] result = validate_task_graph(tasks) if not result.valid: for err in result.errors: print(f'WARNING: {err}', file=sys.stderr) sys.exit(1) print(f'Graph valid: {len(tasks)} tasks, no cycles or orphan refs.') except ImportError: print('pixl engine not installed — skipping graph validation.') "- If cycles or orphan refs detected: warn the user with the specific errors and ask whether to save anyway
- If pixl engine not installed: skip validation gracefully
- If pixl is available, also persist task state to the DB:
pixl artifact put --name task-state --type task_state --content "$(cat .context/task-state.json)" - Report how many tasks were saved
Step 3: Load Task State
- Read
.context/task-state.json - Filter to only
pendingandin_progresstasks (skip completed) - For each task, call
TaskCreatewith the original subject, description, and activeForm - After all tasks are created, restore dependency relationships using
TaskUpdatewithaddBlockedBy - Report how many tasks were restored
- Show the user which tasks are ready to work on (not blocked)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 83 lines · 32 tokens per session scan A 4edeef3ef45d
task-persist is a skill published in the GitHub repository hamzaPixl/pixl-ai (2 stars, last pushed 6mo ago), licensed MIT. It adds 32 tokens to every session and 667 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
Migrate
Intakes external content (notes, CLAUDE.md, Cursor rules, Obsidian/Notion/Apple Notes exports), classifies chunks against the LifeOS taxonomy, and commits with provenance after confidence-tiered approval. USE WHEN /migrate, migrate content, import from other LifeOS, bring in old notes, import Cursor rules, import…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
wiki-dashboard
Create dynamic, queryable Obsidian dashboard views using Bases or Dataview. Use for auto-updating tables, indexes, or structured views of vault content; not for ordinary question answering.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
session-compact
AI DevKit · Compact a historical AI coding session with Jev when context is long, work is handed off or resumed, or durable continuation facts and memory candidates need extraction.
daily-briefing
Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…